You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
* `svd_rrule_min_krylovdim=$(Defaults.svd_rrule_min_krylovdim)` : Minimal Krylov dimension of the reverse-rule algorithm (if it is a Krylov algorithm).
* `svd_rrule_alg=:$(Defaults.svd_rrule_alg)` : Reverse-rule algorithm for the SVD gradient.
33
-
- `:tsvd`: Uses TensorKit's reverse-rule for `tsvd` which doesn't solve any linear problem and instead requires access to the full SVD, see [TensorKit](https://github.com/Jutho/TensorKit.jl/blob/f9cddcf97f8d001888a26f4dce7408d5c6e2228f/ext/TensorKitChainRulesCoreExt/factorizations.jl#L3)
33
+
- `:full`: Uses TensorKit's reverse-rule for `tsvd` which doesn't solve any linear problem and instead requires access to the full SVD, see [TensorKit](https://github.com/Jutho/TensorKit.jl/blob/f9cddcf97f8d001888a26f4dce7408d5c6e2228f/ext/TensorKitChainRulesCoreExt/factorizations.jl#L3)
34
34
- `:gmres`: GMRES iterative linear solver, see the [KrylovKit docs](https://jutho.github.io/KrylovKit.jl/stable/man/algorithms/#KrylovKit.GMRES) for details
35
35
- `:bicgstab`: BiCGStab iterative linear solver, see the [KrylovKit docs](https://jutho.github.io/KrylovKit.jl/stable/man/algorithms/#KrylovKit.BiCGStab) for details
36
36
- `:arnoldi`: Arnoldi Krylov algorithm, see the [KrylovKit docs](https://jutho.github.io/KrylovKit.jl/stable/man/algorithms/#KrylovKit.Arnoldi) for details
37
+
* `svd_rrule_broadening=$(Defaults.svd_rrule_broadening)` : Lorentzian broadening amplitude which smoothens the divergent term in the SVD adjoint in case of (pseudo) degenerate singular values
0 commit comments